The afternoon light filtered weakly through the blinds, casting long, dusty shadows across Emily’s desk. It was a light that made her feel even more sluggish. She was not sleeping well. The information had settled in her mind like a stone. The intern, who was barely out of school, was earning more than her.

She rubbed her temples, trying to massage away the growing ache. The sounds of the office seemed to be a thousand tiny needles poking at her ears. A deep breath.

"Hey, Em! Got that presentation ready for the big meeting?" The voice, cheerful and vibrant, belonged to the intern, Chloe. Emily forced a nod, the words, a dull echo in her own head.

Emotion: tired

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.92 Negative
PC2 (Disposition): -1.00

Role in Research

This story is one of 1,000 stories generated for the emotion tired. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 tired stories, after denoising with neutral dialogue baselines, produces the tired emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the tired vector is projected through the unembedding matrix.

Promoted:
weary0.254
fatigue0.249
😴0.238
sighed0.237
barely0.230
Suppressed:
C-0.268
because-0.225
B-0.219
🤟-0.217
భి-0.214